# robots.txt for CrocLeads
# Last updated: 2026-05-13
# Strategy: allow AI search/citation crawlers, block AI training scrapers
# Canonical crawler list — keep in sync across all Lead Machine sites

# ─── Default: allow all, block auth/dashboard routes ───
User-agent: *
Allow: /
Disallow: /dashboard/
Disallow: /login
Disallow: /register
Disallow: /forgot-password
Disallow: /reset-password

Sitemap: https://crocleads.com/sitemap-index.xml

# ─── Tier 1: Search engines (full access) ───
User-agent: Googlebot
User-agent: Bingbot
User-agent: Applebot
Allow: /
Disallow: /dashboard/
Disallow: /login
Disallow: /register
Disallow: /forgot-password
Disallow: /reset-password

# ─── Tier 2: AI search assistants (citation — ALLOW public pages) ───
# OpenAI — GPTBot is ALLOWED here for citation (supply-side benefits from AI visibility)
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
# Anthropic
User-agent: ClaudeBot
User-agent: Claude-User
# Google AI
User-agent: Gemini-User
User-agent: Gemini-Deep-Research
User-agent: Google-CloudVertexBot
# Perplexity
User-agent: PerplexityBot
User-agent: Perplexity-User
# Others
User-agent: MistralAI-User
User-agent: TavilyBot
User-agent: ExaBot
Allow: /
Disallow: /dashboard/
Disallow: /login
Disallow: /register
Disallow: /forgot-password
Disallow: /reset-password

# ─── Tier 3: Training-only crawlers (BLOCKED — opt out of training datasets) ───
User-agent: CCBot
User-agent: anthropic-ai
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Bytespider
User-agent: Google-Extended
Disallow: /

# ─── Tier 4: SEO scrapers (BLOCKED) ───
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: MJ12bot
User-agent: DotBot
User-agent: BLEXBot
User-agent: PetalBot
Disallow: /